© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129697
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to organizational structure and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iales
    -0.07
     eof
    -0.07
    andom
    -0.06
    º
    -0.06
    inez
    -0.06
    ÑĭваниÑı
    -0.06
     ways
    -0.06
     {!
    -0.06
     Parade
    -0.06
    xious
    -0.06
    POSITIVE LOGITS
    uely
    0.08
    ucci
    0.07
    InvalidOperationException
    0.07
     же
    0.07
    bote
    0.07
     ayrıca
    0.07
    ees
    0.07
    rio
    0.06
    613
    0.06
    ificio
    0.06
    Activations Density 0.062%

    No Known Activations